{"id":"W4416157244","doi":"10.1109/trustcom66490.2025.00125","title":"Enhancing Adversarial Robustness of IoT Intrusion Detection via SHAP-Based Attribution Fingerprinting","year":2025,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Guelph; York University","funders":"National Research Council","keywords":"Adversarial system; Robustness (evolution); Intrusion detection system; Internet of Things; Evasion (ethics); Transparency (behavior); Attack model; Attribution","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002066589,0.0008130663,0.000882963,0.0008420845,0.0003953184,0.00106374,0.001421876,0.001136873,0.001227321],"category_scores_gemma":[0.01193854,0.00038081,0.0008135833,0.0005091667,0.001485412,0.002369309,0.001854851,0.001917277,0.0001783116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001048826,"about_ca_system_score_gemma":0.000860906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001447725,"about_ca_topic_score_gemma":0.001325276,"domain_scores_codex":[0.9989806,0.0004005485,0.00004907426,0.000265538,0.0002004978,0.0001036611],"domain_scores_gemma":[0.9926727,0.004724151,0.0009474949,0.000939956,0.0005135976,0.0002019812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001245943,0.00006220108,0.003525779,0.0000543227,0.000053493,0.0001129467,0.0001023509,0.9396772,0.002116334,0.02008973,0.0007658526,0.03331525],"study_design_scores_gemma":[0.000003875027,0.00001735677,0.0001522307,0.000004237316,0.000005509137,0.00001863632,0.000004135387,0.9897681,0.000492596,0.009422787,0.0001055066,0.000005059645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1379057,0.0003489617,0.8576766,0.0007461986,0.00005187653,0.00006478788,0.0001623584,0.0009588181,0.002084612],"genre_scores_gemma":[0.9692272,0.0001132597,0.02948801,0.0001300759,0.00003230558,0.0000335138,0.0001293026,0.00003535906,0.0008109892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002066589,"threshold_uncertainty_score":0.01092929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007174917290799207,"score_gpt":0.2491510403786483,"score_spread":0.2419761230878491,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}